Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TulanCN/vibe-noveling --skill novel-training-groundgit clone --depth 1 https://github.com/TulanCN/vibe-novelingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tulancn/vibe-noveling/novel-training-ground)<a href="https://agentmods.dev/skills/tulancn/vibe-noveling/novel-training-ground"><img src="https://agentmods.dev/badge/skills/tulancn/vibe-noveling/novel-training-ground/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tulancn/vibe-noveling/novel-training-ground"><img src="https://agentmods.dev/badge/skills/tulancn/vibe-noveling/novel-training-ground.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01072 |
| Opus 5 | $0.00028 | $0.00536 |
| Sonnet 5 | $0.00011 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
novel-training-ground scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
修炼场
在当前对话中直接输出一段非正史的战斗草稿，用于验证角色/物品的战斗设定是否完整、是否符合预期。不生成任何文件。
核心原则：只设定场景框架，不限制内容。任何角色、物品、怪物都可以丢进来配对。
可选背景：万象台
如果你需要一个叙事框架来解释角色为何能在这里随意测试，可以使用以下设定：
混沌残片中铸就的演武之地，悬浮诸界之外。入台者一念可变万象——召对手、换战场、调能力，皆由心意。唯一规则：离台即散，不染因果。 台上体感为真，足验设定之完整。
不需要的话，跳过背景直接进入配置即可。也可以自定义修炼场的形态（如系统空间、梦境战场、虚拟沙盒等）。
第一步：加载战斗设定
根据用户指定的角色/物品，从 memory/entities/ 中只读战斗相关数据：
- 角色：境界、技能/功法、法宝/武器、战斗风格/偏好、体质/血脉
- 物品：功能、使用条件、限制、与其他体系的交互
- 对手：如果指定了已有实体，同样加载其战斗数据
不加载与战斗无关的信息（人际关系、背景故事等）。缺失的战斗设定先补全，不自己编造。
第二步：配置战场
逐项收集配置，每项都可跳过使用默认值：
| 参数 | 说明 | 默认值 |
|---|---|---|
| 出战角色 | 谁上场？支持多角色协同（如主角+伙伴） | 用户指定 |
| 对手 | 已有实体名 / 临时描述（如"同境界剑修，擅长快攻"）/ 模糊指定 / 多个敌人 | 随机生成一个同境界对手 |
| 能力调参 | 临时 buff/nerf（如"境界提到金丹期""禁用飞剑""开局灵力减半"） | 使用当前设定 |
| 战斗风格/连招 | 角色怎么打？可指定流程（如"先防守观察→对方出杀招→闪避反击→飞剑收尾"）、偏好（猛攻/游击/防守反击）、或具体技能释放顺序 | 按角色设定自然发挥 |
| 战场环境 | 在哪打？地形、天气、环境因素（如"峡谷，暴雨""闹市，不能伤平民"） | 通用中立场景 |
| 战斗目标 | 打到什么程度？分出胜负 / 测试特定技能效果 / 只看开场几回合 / 打到一方力竭 | 分胜负 |
配置不要一口气全部问完。先确认出战角色和对手，再逐项收集。
第三步：输出战斗正文
在当前对话中直接输出战斗草稿。按 novel-write 的写作标准来写。注意：
- 能力表达清晰 — 技能/法宝的效果读者能直观感受到，不是数值说明
- 战斗节奏有起伏 — 不是平铺直叙的技能对轰，有压制、反转、喘息
- 角色风格一致 — 战斗方式符合角色设定中的风格偏好
- 多角色协同 — 有配合的角色要写出协同感，不是轮流单挑
- 标明非正史 — 开头注明「修炼场草稿 · 非正史」，用户不会困惑这段算不算正文
根据战斗目标控制篇幅。测试连招就写到连招打完，分胜负就写完整场。
禁止
- 战斗过程中插入诊断分析或评论
- 生成任何文件——只在对话中输出
- 在输出正文前过多追问——配置有默认值的直接用默认值
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 64 lines · 57 tokens per session scan A 94dbe85d4be2
novel-training-ground is a skill published in the GitHub repository TulanCN/vibe-noveling (23 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,072 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
html-ppt-zhangzara-8-bit-orbit
A gamer's journey building a retro-arcade collection — the obsession, the hunt, and what the machines came to mean. Built as a decision-grade story deck for friends, hobby community.
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.
threejs-audio-generator
Generate, convert, clean, and integrate audio for Three.js browser games with ElevenLabs: sound effects, looping ambience, UI sounds, impact/weapon/vehicle audio, creature and boss stingers, announcer and dialogue TTS, voice conversion from a scratch performance, voice cleanup, audio manifests, and Web Audio…
sprite-gen
A pipeline for turning generated 2D game-character images into transparent sprite sheets, which store animation frames for a game.
audio-design
Implement game audio practice — bus/mixer architecture and gain in decibels, ducking (sidechain), adaptive/dynamic music via layering and re-sequencing, SFX variation, and beat synchronization. Engine-neutral. Use when the user mentions audio mixing, audio buses, adaptive/dynamic music, ducking, SFX variation, music…
create-game-assets
Plan, generate, source, normalize, and validate cohesive visual game assets. Use for art direction, style bibles, sprites, tilesets, backgrounds, UI art, icons, textures, concept art, or 3D asset briefs.